© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18968
    Prev
    Next
    INDEX
    Explanations

    punctuation and common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yra
    -0.05
    ष
    -0.05
     wh
    -0.05
    产
    -0.05
    ype
    -0.04
    äss
    -0.04
    -flex
    -0.04
    attle
    -0.04
    ym
    -0.04
    æľ¬åij¨
    -0.04
    POSITIVE LOGITS
    ëŀĮ
    0.07
    zog
    0.07
    åł´æīĢãģ¯
    0.06
    ISI
    0.06
    idon
    0.06
     illus
    0.06
    ampa
    0.06
    chester
    0.06
    Html
    0.06
    emun
    0.06
    Activations Density 0.001%

    No Known Activations